Deepstream deployment of yolov3 does not produce detection boxes

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) jetson tx2
**• DeepStream Version6
**• JetPack Version (valid for Jetson only) 4.6

When I deploy my own yolov3 trained model using deep flow, I can generate the inference engine but cannot get the bounding box. I modified the paresbbox file of yolov3 according to the introduction on the official website. How to deal with it?

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

Hi,

Do you apply the customization mentioned in the document below:
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_custom_YOLO.html

The guidance is for the model retrained with Darknet.
Do you also have .cfg and .weight format via deep flow?

Thanks.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.